← Back to community benchmarks

Qwen3.5-VL-122B-A10B-4bitCRACK

M5 Max (40c) · 128 GB · 4bit · 2026-04-04
Performance
1k
tokens
1,065
PP tok/s
65.9
TG tok/s
961
TTFT (ms)
65.6
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.2
macOS macOS 26.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,065 65.9 65.6 GB current
4k 1,525 62.7 67.0 GB view
8k 1,480 58.9 67.7 GB view